Codex works in this repository as an obsidian-llm-wiki agent host. Follow the same host-neutral workflow contract as Claude Code. Before changing ingest, memory, source registration, project/work-OS behavior, or external workflow…
374mo agoReviewMountCreate a free account to mount
Integrate chubbyguan/chubbyskills as LLM Wiki's local multi-channel ingest pack, turning Chinese feeds, videos, podcasts, articles, and social posts into searchable Obsidian/Markdown knowledge.
374mo agoReviewMountCreate a free account to mount
Capture high-signal X/Twitter posts into an Obsidian vault through the official Obsidian Web Clipper, then let LLM Wiki search, review, and promote the saved notes.
374mo agoReviewMountCreate a free account to mount
Route authorized reverse-engineering, cybersecurity, and CTF tasks through the bundled skills and tool workflows. Use for APK/mobile, native binaries, JavaScript signatures, captured protocols, security assessments, Forefy ASR discovery, and bounded routing evolution.
2610d agoReviewMountCreate a free account to mount
Test authorized REST, GraphQL, WebSocket, and SOAP APIs for authentication, authorization, input validation, and rate-limiting flaws. Use for API security assessments and JWT/OAuth testing.
Reviews a reverse-skill case package for scope readiness, Evidence to Finding to Path traceability, work item coverage, timeline references, and optional artifact hash integrity before report handoff.
2610d agoReviewMountCreate a free account to mount
Decision-skeleton reference for reverse-engineering and security routes. Each file distils the bundled field-journal seeds into scene/criterion/turn lines so an agent can locate its current situation without reading every case record. Use when a routed task needs decision support mid-execution (卡住怎么办/该换维度吗/这个现象说明什么), alongside the selected module's own SKILL.md.
2610d agoReviewMountCreate a free account to mount
generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture/c4-style diagrams, dependency graphs, gantt charts, mind maps, user journeys, sankey-style flows, org charts, network graphs, and other visual models. supports mermaid by default, graphviz dot for complex graph layout, plantuml for uml-heavy engineering diagrams, and svg output when direct markup is more reliable.
Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal report in the user's project directory. Trigger keywords: 写报告, 写文档, 出报告, writeup, 技术文档, report, documentation.
Goal-contract, capability graph, TraceCard, and promotion-gate control plane for self-evolving reverse/security skill routing. Use before macro-routing when the task needs end-to-end completion, route repair, or reusable learning.
2610d agoReviewMountCreate a free account to mount
Ghidra 逆向分析辅助技能(GhydraMCP)。用户提到用 Ghidra 逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO, 或明确不想用 IDA、IDA 当前不可运行时使用此技能。 Use when the user wants to reverse engineer, decompile, or analyze a binary with Ghidra specifically, or as a free alternative when IDA Pro is unavailable. ⚠️ 本仓库尚未用真实项目验证过此技能,见下方"来源与验证状态"。本机最新版 IDA 可运行时优先用 `ida-reverse` (已有本仓库真机验证的踩坑记录);本技能用于 IDA 不可运行、或用户明确要求 Ghidra 的场景。
2610d agoReviewMountCreate a free account to mount
Analyze malware samples using static, dynamic, and behavioral evidence, extract indicators of compromise, and develop YARA or Sigma rules. Use for sample triage, sandbox analysis, and anti-analysis investigation.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.